Skip to main content
Glama

Nansen

by io.github.nansen-ai
OverviewDiscussionsAdmin

Loading technical indicators

token_technical_indicators
Read-only

Get a technical-analysis snapshot for a token: SMA(20/50/200), EMA(12/26), RSI(14), MACD(12,26,9), Bollinger Bands(20, 2σ), ATR(14), and rolling VWAP(20), computed from the last 260 closed candles at an explicit timeframe.

Supports EVM chains and Solana for on-chain tokens, AND Hyperliquid perpetual futures. For Hyperliquid perps, pass chain="hyperliquid" and use the perp symbol as tokenAddress (e.g. "BTC", "HYPE" for native perps; "XYZ:ORDI" for XYZ-namespaced perps — prefix is normalized automatically).

YOU MUST USE THIS for technical analysis instead of computing indicators from raw token_ohlcv candles — it uses far more history (260 closed candles) and charting-platform conventions (SMA-seeded EMA, Wilder RSI/ATR, population-σ Bollinger).

Timeframes (explicit, no auto-resolution):

  • 5m / 15m / 30m / 1h / 4h: intraday and short-horizon analysis

  • 1d (default): swing/position horizon

  • 1w: long-term trend

Output: a snapshot header (candles used, date range, last close, 5-candle price change) plus one row per indicator, each with a 5-candle trend delta so you can read direction, not just level:

  • SMA 20/50/200: values, price vs each, MA slopes

  • EMA 12/26: values, spread %, widening/narrowing

  • RSI(14): level, prior candle, 5-candle change

  • MACD(12,26,9): line/signal/histogram, rising/falling, candles since signal cross

  • Bollinger(20,2σ): bands, %B, bandwidth and its change

  • ATR(14): value and % of price (volatility), rising/falling

  • VWAP(20): value, price vs VWAP

Indicators without enough closed-candle history render as n/a (e.g. SMA200 on young tokens); the candle count used is always reported. VWAP is n/a on Hyperliquid 5m-1h timeframes (volume is NULL in those views) — use 4h or 1d for Hyperliquid VWAP.

Example Usage: Daily technical snapshot for WETH: { "chain": "ethereum", "tokenAddress": "0xc02aaa39b223fe8d0a0e5c4f27ead9083c756cc2", "timeframe": "1d" } 

4-hour snapshot for the BTC Hyperliquid perp:
```
{
    "chain": "hyperliquid",
    "tokenAddress": "BTC",
    "timeframe": "4h"
}
```

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
requestYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and non-destructive, and the description adds substantial behavioral context beyond that: computation from the last 260 closed candles, explicit timeframe with no auto-resolution, n/a behavior for insufficient history, and the Hyperliquid VWAP volume-NULL limitation. This is the kind of behavioral disclosure an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but it is well-organized with sections, bolded callouts, a timeframe list, and concrete examples. It earns most of its length; the detailed per-indicator output bullets are slightly redundant given an output schema exists, so it is not maximally lean.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool covering multiple chains, perp futures, seven timeframes, and seven indicator groups, the description covers all operational edge cases: insufficient-history n/a, Hyperliquid symbol formats, timeframe semantics, VWAP unavailability, and the output shape. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description bears the full burden of explaining parameters, and it delivers. It explains that chain supports EVM/Solana and Hyperliquid, how to encode perp symbols as tokenAddress with namespace normalization, the full timeframe enum and its default, and that results are always computed up to now with no date range. The two JSON examples make the intended 'request' shape unambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Get a technical-analysis snapshot for a token', then enumerates exactly which indicators are computed. It distinguishes itself from the sibling token_ohlcv by explicitly saying it should be used instead of computing indicators from raw candles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance with '**YOU MUST USE THIS** for technical analysis instead of computing indicators from raw token_ohlcv candles' and explains why (more history, charting conventions). It also gives concrete guidance for Hyperliquid perps, timeframe selection by horizon, and the VWAP-on-Hyperliquid caveat.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Nansen toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources